Inference-Time Intervention: Eliciting Truthful Answers from a Language Model https://arxiv.org/abs/2306.03341
via @seeallochnaya

Just find a "truth" direction in latent space and move there

lmao

full graph

Apple Researchers Introduce ByteFormer: An AI Model That Consumes Only Bytes And Does Not Explicitly Model The Input Modality - MarkTechPost
https://www.marktechpost.com/2023/06/09/apple-researchers-introduce-byteformer-an-ai-model-that-consumes-only-bytes-and-does-not-explicitly-model-the-input-modality/

Lectures on high-dimensional probability https://www.math.uci.edu/~rvershyn/teaching/hdp/hdp.html

https://news.uchicago.edu/story/tempest-teacup-uchicago-physicists-make-breakthrough-creating-turbulence
pondering

https://neurosciencenews.com/soybean-oil-genetics-asd-15505/
tldr: causes reduction in oxytocin

Learning how network structure shapes decision-making for bio-inspired computing

Abstract:

To better understand how network structure shapes intelligent behavior, we developed a learning algorithm that we used to build personalized brain network models for 650 Human Connectome Project participants. We found that participants with higher intelligence scores took more time to solve difficult problems, and that slower solvers had higher average functional connectivity. With simulations we identified a mechanistic link between functional connectivity, intelligence, processing speed and brain synchrony for trading accuracy with speed in dependence of excitation-inhibition balance. Reduced synchrony led decision-making circuits to quickly jump to conclusions, while higher synchrony allowed for better integration of evidence and more robust working memory. Strict tests were applied to ensure reproducibility and generality of the obtained results. Here, we identify links between brain structure and function that enable to learn connectome topology from noninvasive recordings and map it to inter-individual differences in behavior, suggesting broad utility for research and clinical applications.

https://www.nature.com/articles/s41467-023-38626-y

An algebraic theory to discriminate qualia in the brain

The mind-brain problem is to bridge relations between in higher mental events and in lower neural events. To address this, some mathematical models have been proposed to explain how the brain can represent the discriminative structure of qualia, but they remain unresolved due to a lack of validation methods. To understand the qualia discrimination mechanism, we need to ask how the brain autonomously develops such a mathematical structure using the constructive approach. In the paper the authors show that a brain model that learns to satisfy an algebraic independence between neural networks separates metric spaces corresponding to qualia types.